[Skip navigation]

Course replaced

This course has been replaced by FMSN20/MASM25: Spatial statistics with image analysis

General Information

The course is held each year during the autumn semester (In 2010, study period HT1) and is worth 7.5 ECTS credits.

Prerequisits

One of:

• Markov processes
• Stationary Stochastic Processes
• Image analysis

Familiarity with Matlab is recommended.

Extent

• 4 hours lectures each week (total 28 h)
• 3 hours computer assignments each week (total 21 h)

Content

The course deals with Bayesian methods for modelling, classification and reconstruction. Markov random fields. Gibbs distributions, deformable templates such as snakes. Correlation structures, multivariate techniques, discriminant analysis. Simualtion methods for inference (MCMC).
Remote sensing and spatial statistics

Examination

Examination consists of home assignments which will be handed out during the course. Possible assignments include:

• Geotechnology and mineralogy
• Remote sensing
• Environmental statistics
• Shape analysis in e.g. computer vision, medical image analysis.

Literature

F. Lindgren, Image Modelling and Estimation - A statistical approach. The Compendium is available from the department or from the literature homepage.

People

Course administration and lecturers (HT10)

Johan Lindström, MH:245
phone: 046-222 40 60
e-mail: johanl@maths.lth.se

Recommended related courses (not prerequisits)

Monte-Carlo-based methods for statistical inference 7.5hp, HT, LP1
Computer vision 6hp, VT, LP1